Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back.

A closed-loop, autonomous molecular discovery platform driven by integrated machine learning tools was developed to accelerate the design of molecules with desired properties. We demonstrated two case studies on dye-like molecules, targeting absorption wavelength, lipophilicity, and photooxidative stability. In the first study, the platform experimentally realized 294 unreported molecules across three automatic iterations of molecular design-make-test-analyze cycles while exploring the structure-function space of four rarely reported scaffolds. In each iteration, the property prediction models that guided exploration learned the structure-property space of diverse scaffold derivatives, which were realized with multistep syntheses and a variety of reactions. The second study exploited property models trained on the explored chemical space and previously reported molecules to discover nine top-performing molecules within a lightly explored structure-property space.

Heterogeneous photochemical reaction enabled by an ultrasonic microreactor.

The presence of solids as starting reagents/reactants or products in flow photochemical reactions can lead to reactor clogging and yield reduction from side reactions. We address this limitation with a new ultrasonic microreactor for continuous solid-laden photochemical reactions. The ultrasonic photochemical microreactor is characterized by the liquid and solid residence time distribution (RTD) and the absorbed photon flux in the reactor via chemical actinometry. The solid-handling capability of the ultrasonic photochemical microreactor is demonstrated with a silyl radical-mediated metallaphotoredox cross-electrophile coupling with a solid base as a reagent.

Parallel multi-droplet platform for reaction kinetics and optimization.

We present an automated droplet reactor platform possessing parallel reactor channels and a scheduling algorithm that orchestrates all of the parallel hardware operations and ensures droplet integrity as well as overall efficiency. We design and incorporate all of the necessary hardware and software to enable the platform to be used to study both thermal and photochemical reactions. We incorporate a Bayesian optimization algorithm into the control software to enable reaction optimization over both categorical and continuous variables. We demonstrate the capabilities of both the preliminary single-channel and parallelized versions of the platform using a series of model thermal and photochemical reactions. We conduct a series of reaction optimization campaigns and demonstrate rapid acquisition of the data necessary to determine reaction kinetics. The platform is flexible in terms of use case: it can be used either to investigate reaction kinetics or to perform reaction optimization over a wide range of chemical domains.

Computer-assisted multistep chemoenzymatic retrosynthesis using a chemical synthesis planner.

Chemoenzymatic synthesis methods use organic and enzyme chemistry to synthesize a desired small molecule. Complementing organic synthesis with enzyme-catalyzed selective transformations under mild conditions enables more sustainable and synthetically efficient chemical manufacturing. Here, we present a multistep retrosynthesis search algorithm to facilitate chemoenzymatic synthesis of pharmaceutical compounds, specialty chemicals, commodity chemicals, and monomers. First, we employ the synthesis planner ASKCOS to plan multistep syntheses starting from commercially available materials. Then, we identify transformations that can be catalyzed by enzymes using a small database of biocatalytic reaction rules previously curated for RetroBioCat, a computer-aided synthesis planning tool for biocatalytic cascades. Enzymatic suggestions captured by the approach include ones capable of reducing the number of synthetic steps. We successfully plan chemoenzymatic routes for active pharmaceutical ingredients or their intermediates (e.g., Sitagliptin, Rivastigmine, and Ephedrine), commodity chemicals (e.g., acrylamide and glycolic acid), and specialty chemicals (e.g., S-Metalochlor and Vanillin), in a retrospective fashion. In addition to recovering published routes, the algorithm proposes many sensible alternative pathways. Our approach provides a chemoenzymatic synthesis planning strategy by identifying synthetic transformations that could be candidates for enzyme catalysis.

Community Resource for Innovation in Polymer Technology (CRIPT): A Scalable Polymer Material Data Structure.

The Community Resource for Innovation in Polymer Technology (CRIPT) data model is designed to address the high complexity in defining a polymer structure and the intricacies involved with characterizing material properties.

Open-Source Chromatographic Data Analysis for Reaction Optimization and Screening.

Automation and digitalization solutions in the field of small molecule synthesis face new challenges for chemical reaction analysis, especially in the field of high-performance liquid chromatography (HPLC). Chromatographic data remains locked in vendors' hardware and software components, limiting their potential in automated workflows and data science applications. In this work, we present an open-source Python project called MOCCA for the analysis of HPLC-DAD (photodiode array detector) raw data. MOCCA provides a comprehensive set of data analysis features, including an automated peak deconvolution routine of known signals, even if overlapped with signals of unexpected impurities or side products. We highlight the broad applicability of MOCCA in four studies: (i) a simulation study to validate MOCCA's data analysis features; (ii) a reaction kinetics study on a Knoevenagel condensation reaction demonstrating MOCCA's peak deconvolution feature; (iii) a closed-loop optimization study for the alkylation of 2-pyridone without human control during data analysis; (iv) a well plate screening of categorical reaction parameters for a novel palladium-catalyzed cyanation of aryl halides employing O-protected cyanohydrins. By publishing MOCCA as a Python package with this work, we envision an open-source community project for chromatographic data analysis with the potential of further advancing its scope and capabilities.

Machine-Learning-Guided Discovery of Electrochemical Reactions.

The molecular structures synthesizable by organic chemists dictate the molecular functions they can create. The invention and development of chemical reactions are thus critical for chemists to access new and desirable functional molecules in all disciplines of organic chemistry. This work seeks to expedite the exploration of emerging areas of organic chemistry by devising a machine-learning-guided workflow for reaction discovery. Specifically, this study uses machine learning to predict competent electrochemical reactions. To this end, we first develop a molecular representation that enables the production of general models with limited training data. Next, we employ automated experimentation to test a large number of electrochemical reactions. These reactions are categorized as competent or incompetent mixtures, and a classification model was trained to predict reaction competency. This model is used to screen 38,865 potential reactions in silico, and the predictions are used to identify a number of reactions of synthetic or mechanistic interest, 80% of which are found to be competent. Additionally, we provide the predictions for the 38,865-member set in the hope of accelerating the development of this field. We envision that adopting a workflow such as this could enable the rapid development of many fields of chemistry.

Building Chemical Property Models for Energetic Materials from Small Datasets Using a Transfer Learning Approach.

For many experimentally measured chemical properties that cannot be directly computed from first-principles, the existing physics-based models do not extrapolate well to out-of-sample molecules, and experimental datasets themselves are too small for traditional machine learning (ML) approaches. To overcome these limitations, we apply a transfer learning approach, whereby we simultaneously train a multi-target regression model on a small number of molecules with experimentally measured values and a large number of molecules with related computed properties. We demonstrate this methodology on predicting the experimentally measured impact sensitivity of energetic crystals, finding that both characteristics of the computed dataset and model architecture are important to prediction accuracy of the small experimental dataset. Our directed-message passing neural network (D-MPNN) ML model using transfer learning outperforms direct-ML and physics-based models on a diverse test set, and the new methods described here are widely applicable to modeling many other structure-property relationships.

Bayesian Optimization of Computer-Proposed Multistep Synthetic Routes on an Automated Robotic Flow Platform.

Computer-aided synthesis planning (CASP) tools can propose retrosynthetic pathways and forward reaction conditions for the synthesis of organic compounds, but the limited availability of context-specific data currently necessitates experimental development to fully specify process details. We plan and optimize a CASP-proposed and human-refined multistep synthesis route toward an exemplary small molecule, sonidegib, on a modular, robotic flow synthesis platform with integrated process analytical technology (PAT) for data-rich experimentation. Human insights address catalyst deactivation and improve yield by strategic choices of order of addition. Multi-objective Bayesian optimization identifies optimal values for categorical and continuous process variables in the multistep route involving 3 reactions (including heterogeneous hydrogenation) and 1 separation. The platform's modularity, robotic reconfigurability, and flexibility for convergent synthesis are shown to be essential for allowing variation of downstream residence time in multistep flow processes and controlling the order of addition to minimize undesired reactivity. Overall, the work demonstrates how automation, machine learning, and robotics enhance manual experimentation through assistance with idea generation, experimental design, execution, and optimization.

Similarity based enzymatic retrosynthesis.

Enzymes synthesize complex natural products effortlessly by catalyzing chemo-, regio-, and enantio-selective transformations. Further, biocatalytic processes are increasingly replacing conventional organic synthesis steps because they use mild solvents, avoid the use of metals, and reduce overall non-biodegradable waste. Here, we present a single-step retrosynthesis search algorithm to facilitate enzymatic synthesis of natural product analogs. First, we develop a tool, RDEnzyme, capable of extracting and applying stereochemically consistent enzymatic reaction templates, i.e., subgraph patterns that describe the changes in connectivity between a product molecule and its corresponding reactant(s). Using RDEnzyme, we demonstrate that molecular similarity is an effective metric to propose retrosynthetic disconnections based on analogy to precedent enzymatic reactions in UniProt/RHEA. Using ∼5500 reactions from RHEA as a knowledge base, the recorded reactants to the product are among the top 10 proposed suggestions in 71% of ∼700 test reactions. Second, we trained a statistical model capable of discriminating between reaction pairs belonging to homologous enzymes and evolutionarily distant enzymes using ∼30 000 reaction pairs from SwissProt as a knowledge base. This model is capable of understanding patterns in enzyme promiscuity to evaluate the likelihood of experimental evolution success. By recursively applying the similarity-based single-step retrosynthesis and evolution prediction workflow, we successfully plan the enzymatic synthesis routes for both active pharmaceutical ingredients (e.g. Islatravir, Molnupiravir) and commodity chemicals (e.g. 1,4-butanediol, branched-chain higher alcohols/biofuels), in a retrospective fashion. Through the development and demonstration of the single-step enzymatic retrosynthesis strategy using natural transformations, our approach provides a first step towards solving the challenging problem of incorporating both enzyme- and organic-chemistry based transformations into a computer aided synthesis planning workflow.

Photochemical Synthesis of the Bioactive Fragment of Salbutamol and Derivatives in a Self-Optimizing Flow Chemistry Platform.

The implementation of self-optimizing flow reactors has been mostly limited to model reactions or known synthesis routes. In this work, a self-optimizing flow photochemistry platform is used to develop an original synthesis of the bioactive fragment of Salbutamol and derivatives. The key photochemical steps for the construction of the aryl vicinyl amino alcohol moiety consist of a C-C bond forming reaction followed by an unprecedented, high yielding (>80 %), benzylic oxidative cyclization.

Automation and Microfluidics for the Efficient, Fast, and Focused Reaction Development of Asymmetric Hydrogenation Catalysis.

Automation and microfluidic tools potentially enable efficient, fast, and focused reaction development of complex chemistries, while minimizing resource- and material consumption. The introduction of automation-assisted workflows will contribute to the more sustainable development and scale-up of new and improved catalytic technologies. Herein, the application of automation and microfluidics to the development of a complex asymmetric hydrogenation reaction is described. Screening and optimization experiments were performed using an automated microfluidic platform, which enabled a drastic reduction in the material consumption compared to conventional laboratory practices. A suitable catalytic system was identified from a library of RuII -diamino precatalysts. In situ precatalyst activation was studied with 1 H/31 P nuclear magnetic resonance (NMR), and the reaction was scaled up to multigram quantities in a batch autoclave. These reactions were monitored using an automated liquid-phase sampling system. Ultimately, in less than a week of total experimental time, multigram quantities of the target enantiopure alcohol product were provided by this automation-assisted approach.

Microfluidic Squeezing Enables MHC Class I Antigen Presentation by Diverse Immune Cells to Elicit CD8+ T Cell Responses with Antitumor Activity.

CD8+ T cell responses are the foundation of the recent clinical success of immunotherapy in oncologic indications. Although checkpoint inhibitors have enhanced the activity of existing CD8+ T cell responses, therapeutic approaches to generate Ag-specific CD8+ T cell responses have had limited success. Here, we demonstrate that cytosolic delivery of Ag through microfluidic squeezing enables MHC class I presentation to CD8+ T cells by diverse cell types. In murine dendritic cells (DCs), squeezed DCs were ∼1000-fold more potent at eliciting CD8+ T cell responses than DCs cross-presenting the same amount of protein Ag. The approach also enabled engineering of less conventional APCs, such as T cells, for effective priming of CD8+ T cells in vitro and in vivo. Mixtures of immune cells, such as murine splenocytes, also elicited CD8+ T cell responses in vivo when squeezed with Ag. We demonstrate that squeezing enables effective MHC class I presentation by human DCs, T cells, B cells, and PBMCs and that, in clinical scale formats, the system can squeeze up to 2 billion cells per minute. Using the human papillomavirus 16 (HPV16) murine model, TC-1, we demonstrate that squeezed B cells, T cells, and unfractionated splenocytes elicit antitumor immunity and correlate with an influx of HPV-specific CD8+ T cells such that >80% of CD8s in the tumor were HPV specific. Together, these findings demonstrate the potential of cytosolic Ag delivery to drive robust CD8+ T cell responses and illustrate the potential for an autologous cell-based vaccine with minimal turnaround time for patients.

Automated Chemical Reaction Extraction from Scientific Literature.

Access to structured chemical reaction data is of key importance for chemists in performing bench experiments and in modern applications like computer-aided drug design. Existing reaction databases are generally populated by human curators through manual abstraction from published literature (e.g., patents and journals), which is time consuming and labor intensive, especially with the exponential growth of chemical literature in recent years. In this study, we focus on developing automated methods for extracting reactions from chemical literature. We consider journal publications as the target source of information, which are more comprehensive and better represent the latest developments in chemistry compared to patents; however, they are less formulaic in their descriptions of reactions. To implement the reaction extraction system, we first devised a chemical reaction schema, primarily including a central product, and a set of associated reaction roles such as reactants, catalyst, solvent, and so on. We formulate the task as a structure prediction problem and solve it with a two-stage deep learning framework consisting of product extraction and reaction role labeling. Both models are built upon Transformer-based encoders, which are adaptively pretrained using domain and task-relevant unlabeled data. Our models are shown to be both effective and data efficient, achieving an F1 score of 76.2% in product extraction and 78.7% in role extraction, with only hundreds of annotated reactions.

The Open Reaction Database.

Chemical reaction data in journal articles, patents, and even electronic laboratory notebooks are currently stored in various formats, often unstructured, which presents a significant barrier to downstream applications, including the training of machine-learning models. We present the Open Reaction Database (ORD), an open-access schema and infrastructure for structuring and sharing organic reaction data, including a centralized data repository. The ORD schema supports conventional and emerging technologies, from benchtop reactions to automated high-throughput experiments and flow chemistry. The data, schema, supporting code, and web-based user interfaces are all publicly available on GitHub. Our vision is that a consistent data representation and infrastructure to support data sharing will enable downstream applications that will greatly improve the state of the art with respect to computer-aided synthesis planning, reaction prediction, and other predictive chemistry tasks.

Direct Optimization across Computer-Generated Reaction Networks Balances Materials Use and Feasibility of Synthesis Plans for Molecule Libraries.

The synthesis of thousands of candidate compounds in drug discovery and development offers opportunities for computer-aided synthesis planning to simplify the synthesis of molecule libraries by leveraging common starting materials and reaction conditions. We develop an optimization-based method to analyze large organic chemical reaction networks and design overlapping synthesis plans for entire molecule libraries so as to minimize the overall number of unique chemical compounds needed as either starting materials or reaction conditions. We consider multiple objectives, including the number of starting materials, the number of catalysts/solvents/reagents, and the likelihood of success of the overall syntheses plan, to select an optimal reaction network to access the target molecules. The library synthesis planning task was formulated as a network flow optimization problem, and we design an efficient decomposition scheme that reduces solution time by a factor of 5 and scales to instance with 48 target molecules and nearly 8000 intermediate reactions within hours. In four case studies of pharmaceutical compounds, the approach reduces the number of starting materials and catalysts/solvents/reagents needed by 32.2 and 66.0% on average and up to 63.2 and 80.0% in the best cases. The code implementation can be found at https://github.com/Coughy1991/Molecule_library_synthesis.

A Multifunctional Microfluidic Platform for High-Throughput Experimentation of Electroorganic Chemistry.

Electroorganic synthesis is a promising tool to design sustainable transformations and discover new reactivities. However, the added setup complexity caused by electrodes in the system impedes efficient screening of reaction conditions. Herein, we present a microfluidic platform that enables automated high-throughput experimentation (HTE) for electroorganic synthesis at a 15-microliter scale. Two HTE modules are demonstrated: 1) the rapid electrochemical reaction condition screening for a radical-radical cross-coupling reaction on micro-fabricated interdigitated electrodes, and 2) measurements of kinetics for mediated anodic oxidations using the microliter-scale cyclic voltammetry. The presented modular approach could be deployed for a range of other electroorganic chemistry applications beyond the demonstrated functionalities.

Microfluidic electrochemistry for single-electron transfer redox-neutral reactions.

Electrochemistry offers opportunities to promote single-electron transfer (SET) redox-neutral chemistries similar to those recently discovered using visible-light photocatalysis but without the use of an expensive photocatalyst. Herein, we introduce a microfluidic redox-neutral electrochemistry (µRN-eChem) platform that has broad applicability to SET chemistry, including radical-radical cross-coupling, Minisci-type reactions, and nickel-catalyzed C(sp2)-O cross-coupling. The cathode and anode simultaneously generate the corresponding reactive intermediates, and selective transformation is facilitated by the rapid molecular diffusion across a microfluidic channel that outpaces the decomposition of the intermediates. µRN-eChem was shown to enable a two-step gram-scale electrosynthesis of a nematic liquid crystal compound, demonstrating its practicality.

Data Augmentation and Pretraining for Template-Based Retrosynthetic Prediction in Computer-Aided Synthesis Planning.

This work presents efforts to augment the performance of data-driven machine learning algorithms for reaction template recommendation used in computer-aided synthesis planning software. Often, machine learning models designed to perform the task of prioritizing reaction templates or molecular transformations are focused on reporting high-accuracy metrics for the one-to-one mapping of product molecules in reaction databases to the template extracted from the recorded reaction. The available templates that get selected for inclusion in these machine learning models have been previously limited to those that appear frequently in the reaction databases and exclude potentially useful transformations. By augmenting open-access data sets of organic reactions with explicitly calculated template applicability and pretraining a template-relevance neural network on this augmented applicability data set, we report an increase in the template applicability recall and an increase in the diversity of predicted precursors. The augmentation and pretraining effectively teaches the neural network an increased set of templates that could theoretically lead to successful reactions for a given target. Even on a small data set of well-curated reactions, the data augmentation and pretraining methods resulted in an increase in top-1 accuracy, especially for rare templates, indicating that these strategies can be very useful for small data sets.